buzz_presence

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint/idempotentHint/non-destructive, so the safety bar is lower, and the description still adds real behavioral substance: only relay-signed presence (NIP-11 self key) is trusted, and any subject without a record is reported as offline. That trust model is exactly the kind of context annotations cannot convey. It does not cover failure behavior or latency/rate considerations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Tightly front-loaded with the purpose, then the two modes, then the trust caveat — no wasted sentences. The trailing "Read-only" duplicates the readOnlyHint annotation and could be dropped, which is the only bit of filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple two-parameter read tool this covers most of what's needed, but neither parameter is required, so the behavior of a call with no arguments is undefined. With no output schema, the description also never hints at the return shape (per-user status records, what a channel lookup yields), leaving the agent to guess at the response.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so 3 would be the baseline, but the description goes beyond the schema's terse "people to look up" by enumerating accepted identifier forms (npub / hex / email in wire mode / exact display name), which materially affects how an agent formats arguments. The channel parameter's "name or id" merely restates the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb+resource ("Who's online: presence") and lays out the two lookup modes — a list of people via `users` or a channel's members via `channel`. It does not explicitly distinguish itself from adjacent siblings like buzz_whoami or buzz_channel_members, so differentiation is left partly to inference.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The two usage modes are described clearly enough to pick the right parameter, which implies when to use it. There is no explicit when-not-to-use guidance and no named alternative (e.g., "to list channel membership rather than presence, use buzz_channel_members"), so an agent must reason about overlap with sibling tools itself.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.